Higgs Audio Demo
Scalable and Versatile 3D Generation from text prompt
VGGT (CVPR 2025)
MoGe live demo
Monocular metric-scale geometry estimation
Generate depth maps from images
Generate surface normals from images
Image-to-3D Generation
Neta's latest text-to-image model
Generate 3D model rigging for animations
Create a custom song with lyrics and optional prompts
Run 3D human pose estimation with images
Customize images using text prompts and styles
Transform images into artistic styles